Sneak paths effects in CBRAM memristive devices arrays for spiking neural networks

D. Roclin (1) , O. Bichler (1) , C. Gamrat (1) , J.-O. Klein (2)

1 DACLE-LIST - Département d'Architectures, Conception et Logiciels Embarqués-LIST
2 IEF - Institut d'électronique fondamentale

In this paper, we study the effects of sneak paths and parasitic metal line resistance in arrays of CBRAM memristive devices operating as synapses for spiking neural networks. Three structures of crosspoint array are reviewed: the crossbar (1R), the anode connected matrix (1T-IR) and the cathode connected matrix (1T-IR). We show that the crossbar is an energy-consuming structure with high leakage during SET/RESET and with an increased switching time due to voltage drops along the lines. Furthermore, we show that parasitic line resistance can have a significant impact on the read resistance of the devices, depending on their location in the crossbar.

Keywords: Electrodes; Memristors; Nanotechnology; Cross-point array; Line resistance; Metal line; Spiking neural networks; Switching time; Voltage drop; Neural networks

Domains: Engineering Sciences [physics]

D. Roclin, O. Bichler, C. Gamrat, J.-O. Klein. Sneak paths effects in CBRAM memristive devices arrays for spiking neural networks. 2014 IEEE/ACM International Symposium on Nanoscale Architectures (NANOARCH), Oct 2014, Paris, France. pp.13-18, ⟨10.1109/NANOARCH.2014.6880501⟩. ⟨cea-01839862⟩